activity
20162022
most citedSqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud

57 citations · 253 across the 17 of their papers we have counts for

collaborators
Showing cs.ROShow all

1 paper · 1 filter

cs.RO2021★ 2 cited

You Only Group Once: Efficient Point-Cloud Processing with Token Representation and Relation Inference Module

Chenfeng Xu, Bohan Zhai, Bichen Wu +5

3D point-cloud-based perception is a challenging but crucial computer vision task. A point-cloud consists of a sparse, unstructured, and unordered set of points. To understand a po…